Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 771 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 6.1064. Min Range: -6.1064

Max Act: 6.1064. Min Act: -0.1700

Data Index: 5996547 (Open Web Text)

Max Activating Token Index: 511

Text #1

Max Range: 6.1064. Min Range: -6.1064

Max Act: 6.0666. Min Act: -0.1700

Data Index: 4909224 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.9893. Min Act: -0.1700

Data Index: 5063510 (Open Web Text)

Max Activating Token Index: 252

Text #3

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.9792. Min Act: -0.1700

Data Index: 3818712 (Open Web Text)

Max Activating Token Index: 610

Text #4

Max Range: 6.1064. Min Range: -6.1064

Max Act: 6.0307. Min Act: -0.1700

Data Index: 8386834 (Open Web Text)

Max Activating Token Index: 824

Text #5

Max Range: 6.1064. Min Range: -6.1064

Max Act: 6.0762. Min Act: -0.1700

Data Index: 1434720 (Open Web Text)

Max Activating Token Index: 232

Text #6

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.9261. Min Act: -0.1700

Data Index: 4631963 (Open Web Text)

Max Activating Token Index: 365

Text #7

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.9039. Min Act: -0.1700

Data Index: 464937 (Open Web Text)

Max Activating Token Index: 352

Text #8

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.8891. Min Act: -0.1700

Data Index: 77770 (Open Web Text)

Max Activating Token Index: 629

Text #9

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.9585. Min Act: -0.1700

Data Index: 5960085 (Open Web Text)

Max Activating Token Index: 532

Text #10

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.8683. Min Act: -0.1700

Data Index: 5669154 (Open Web Text)

Max Activating Token Index: 463

Text #11

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.8590. Min Act: -0.1700

Data Index: 3015740 (Open Web Text)

Max Activating Token Index: 145

Text #12

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.8824. Min Act: -0.1700

Data Index: 304193 (Open Web Text)

Max Activating Token Index: 533

Text #13

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.8340. Min Act: -0.1700

Data Index: 3596415 (Open Web Text)

Max Activating Token Index: 758

Text #14

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.7640. Min Act: -0.1700

Data Index: 39879 (Open Web Text)

Max Activating Token Index: 523

Text #15

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.7880. Min Act: -0.1700

Data Index: 421877 (Open Web Text)

Max Activating Token Index: 170

Text #16

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.8403. Min Act: -0.1700

Data Index: 1142290 (Open Web Text)

Max Activating Token Index: 406

Text #17

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.7207. Min Act: -0.1700

Data Index: 4118521 (Open Web Text)

Max Activating Token Index: 770

Text #18

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.8122. Min Act: -0.1700

Data Index: 7586355 (Open Web Text)

Max Activating Token Index: 84

Text #19

Max Range: 6.1064. Min Range: -6.1064

Max Act: 5.8488. Min Act: -0.1700

Data Index: 5608108 (Open Web Text)

Max Activating Token Index: 810